Can the Mac 24 GB run Stable Diffusion 3.5 Large?
Yes, but only just: 16-bit leaves 0.8 GB free on the Mac 24 GB.
16-bit (16.5 GB) fits with only 0.8 GB to spare (about 18.8 GB of 19.6 GB).
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | sd3.5_large.safetensors 16-bit · stabilityai/stable-diffusion-3.5-large | models/diffusion_models | 16.5 GB | Download → |
| Text encoder | t5-v1_1-xxl-encoder-Q8_0.gguf T5-XXL GGUF Q8_0 · city96/t5-v1_1-xxl-encoder-gguf | models/text_encoders | 5.1 GB | Download → |
| Text encoder | clip_l.safetensors CLIP-L · Comfy-Org/stable-diffusion-3.5-fp8 | models/text_encoders | 0.2 GB | Download → |
| Text encoder | clip_g.safetensors CLIP-G · Comfy-Org/stable-diffusion-3.5-fp8 | models/text_encoders | 1.4 GB | Download → |
| VAE | diffusion_pytorch_model.safetensors SD 3.5 VAE (gated repo: log in and accept the licence first) · stabilityai/stable-diffusion-3.5-large | models/vae | 0.2 GB | Download → |
| Total download · keep about the same free on disk | 23.3 GB | |||
Alternatives: T5-XXL FP16 (9.8 GB). On a Mac, FP8 text encoders do not load, so a 16-bit one is listed - or a GGUF one, loaded with “CLIPLoader (GGUF)” from the ComfyUI-GGUF nodes. Sizes from Hugging Face, 2026-10-01.
Shared memory: about 29.3 GB of your 24 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That is about 5.3 GB more than there is. It still runs: while the model works, the system compresses or swaps the idle text encoder, so loading and changing the prompt get slower. A smaller file or text encoder avoids that. calculated
02Every SD 3.5 Large file on 19.6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · stabilityai | 16.5 GB | 18.8 GB | fits · 0.8 GB spare | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 8.8 GB | 11.1 GB | fits · 8.5 GB spare | practically identical to the original | Hugging Face → |
| Q5_1 GGUF · city96 | 6.3 GB | 8.6 GB | fits · 11.0 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_1 GGUF · city96 | 5.3 GB | 7.6 GB | fits · 12.0 GB spare | good; some loss in fine detail and text | Hugging Face → |
“Needed” adds 1.5 GB of working memory for SD 3.5 Large and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run SD 3.5 Large on a Mac 24 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the Mac 24 GB
A Mac with 24 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 19.6 GB of it by default (older macOS versions: about 17.2 GB); that is the figure used here. ComfyUI can go past it, but macOS then starts compressing and swapping memory and everything slows down. ComfyUI runs on Apple GPUs through PyTorch's MPS backend. 16-bit and GGUF files work; FP8 and INT8 files do not save memory on a Mac, so they are skipped. Speed is the catch: even the fastest Macs are several times slower per image than a desktop RTX card. Chips sold with 24 GB: M2, M3, M4, M4 Pro, M5, M5 Pro, M6 (memory bandwidth 100–307 GB/s - the higher, the faster). Everything about Macs and local AI →
24 GB unified · ~19.6 GB for the GPU · 100–307 GB/s · Apple Silicon. Everything that runs on it →
05Questions
How much VRAM does SD 3.5 Large need?
Around 7.6 GB with the smallest file (Q4_1) and 11.1 GB with an 8-bit file (Q8_0). The full 16-bit file needs about 18.8 GB.
Which SD 3.5 Large file should I download for the Mac 24 GB?
16-bit (16.5 GB) from stabilityai/stable-diffusion-3.5-large.
How much do I need to download for SD 3.5 Large on the Mac 24 GB?
23.3 GB: sd3.5_large.safetensors, t5-v1_1-xxl-encoder-Q8_0.gguf, clip_l.safetensors, clip_g.safetensors, diffusion_pytorch_model.safetensors.